Activate or Not: Learning Customized Activation · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2009.04759/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTActivate or Not: Learning Customized Activation — mentioned by porridgeraisinhttps://news.ycombinator.com/item?id=43195700urn:hackerpapers:mention:2009.04759:43195700Thu, 27 Feb 2025 16:12:21 GMT<p>This idea exists (the broad field is called neural architecture search), although you have to parameterize it somehow to allow gradient descent to happen. Here are examples: https://arxiv.org/abs/2009.04759 https://arxiv.org/abs/1906.09529</p><p><a href="https://hackerpaper.kaipfister.de/p/2009.04759/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV